paper-with-me

Papers

Logarithmic Memory Networks (LMNs): Efficient Long-Range Sequence Modeling for Resource-Constrained Environments

2025-01-14 · Mohamed A. Taha

Long-range sequence modeling is a crucial aspect of natural language processing and time series analysis. However, traditional models like Recurrent Neural Networks (RNNs) and Transformers suffer from computational and memory inefficiencies, especially when dealing with long sequences. This paper introduces Logarithmic Memory Networks (LMNs), a novel architecture that leverages a hierarchical logarithmic tree structure to efficiently store and retrieve past information. LMNs dynamically summarize historical context, significantly reducing the memory footprint and computational complexity of attention mechanisms from O(n2) to O(log(n)). The model employs a single-vector, targeted attention mechanism to access stored information, and the memory block construction worker (summarizer) layer operates in two modes: a parallel execution mode during training for efficient processing of hierarchical tree structures and a sequential execution mode during inference, which acts as a memory management system. It also implicitly encodes positional information, eliminating the need for explicit positional encodings. These features make LMNs a robust and scalable solution for processing long-range sequences in resource-constrained environments, offering practical improvements in efficiency and scalability. The code is publicly available under the MIT License on GitHub: https://github.com/AhmedBoin/LogarithmicMemory.

📄 PDF Abstract BibTeX arXiv:2501.07905

Code (1)

ahmedboin/logarithmicmemory 공식 구현 pytorch

Tasks

Time Series Analysis

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Labeled Memory Networks for Online Model Adaptation

2017-07-05 · Shiv Shankar, Sunita Sarawagi

Augmenting a neural network with memory that can grow without growing the number of trained parameters is a recent powerful concept with many exciting applications. We propose a design of memory augmented neural networks…

Few-Shot LearningMeta-Learningmodel

Feedforward Controllers from Learned Dynamic Local Model Networks with Application to Excavator Assistance Functions

2024-09-25 · Leon Greiser, Ozan Demir, Benjamin Hartmann, Henrik Hose 외

Complicated first principles modelling and controller synthesis can be prohibitively slow and expensive for high-mix, low-volume products such as hydraulic excavators. Instead, in a data-driven approach, recorded traject…

valid

Gradual Forgetting: Logarithmic Compression for Extending Transformer Context Windows

2025-10-25 · Billy Dickson, Zoran Tiganj arxiv

Most approaches to long-context processing increase the complexity of the transformer's internal architecture by integrating mechanisms such as recurrence or auxiliary memory modules. In this work, we introduce an altern…

Adaptive Memory Decay for Log-Linear Attention

2026-05-07 · Yaxita Amin, Helen Zichen Li, Mengfan Zhang, Samet Ayhan arxiv

Sequence models face a fundamental tradeoff between memory capacity and computational efficiency. Transformers achieve expressive context modeling at quadratic cost, while linear attention and state-space models run in l…

Computational Efficiency

HOPE for a Robust Parameterization of Long-memory State Space Models

2024-05-22 · Annan Yu, Michael W. Mahoney, N. Benjamin Erichson

State-space models (SSMs) that utilize linear, time-invariant (LTI) systems are known for their effectiveness in learning long sequences. To achieve state-of-the-art performance, an SSM often needs a specifically designe…

State Space Models